Story Generation with Rich Details

Fangzhou Zhai, Vera Demberg, Alexander Koller


Abstract
Automatically generated stories need to be not only coherent, but also interesting. Apart from realizing a story line, the text also needs to include rich details to engage the readers. We propose a model that features two different generation components: an outliner, which proceeds the main story line to realize global coherence; a detailer, which supplies relevant details to the story in a locally coherent manner. Human evaluations show our model substantially improves the informativeness of generated text while retaining its coherence, outperforming various baselines.
Anthology ID:
2020.coling-main.212
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2346–2351
Language:
URL:
https://aclanthology.org/2020.coling-main.212
DOI:
10.18653/v1/2020.coling-main.212
Bibkey:
Cite (ACL):
Fangzhou Zhai, Vera Demberg, and Alexander Koller. 2020. Story Generation with Rich Details. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2346–2351, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Story Generation with Rich Details (Zhai et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.coling-main.212.pdf